© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107462
    Prev
    Next
    INDEX
    Explanations

    identifying functional sequence alignments

    np_acts-logits-general · gemini-2.5-flash-lite

    bioinformatics and sequence alignment terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rei
    -0.87
    нув
    -0.73
    Sede
    -0.71
     harrowing
    -0.69
    ơn
    -0.69
    想像
    -0.68
     gén
    -0.67
    Holo
    -0.66
    числи
    -0.66
     snapping
    -0.66
    POSITIVE LOGITS
     alignment
    0.89
     Align
    0.88
     Consensus
    0.83
     alignments
    0.81
     profile
    0.80
    hmm
    0.79
     family
    0.77
     hmm
    0.76
    Consensus
    0.75
     Pf
    0.74
    Activations Density 0.055%

    No Known Activations